ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914876790669312 |
|---|---|
| author | Chen, Binghui Li, Wenyu Geng, Yifeng Xie, Xuansong Zuo, Wangmeng |
| author_facet | Chen, Binghui Li, Wenyu Geng, Yifeng Xie, Xuansong Zuo, Wangmeng |
| contents | With the development of the large-scale diffusion model, Artificial Intelligence Generated Content (AIGC) techniques are popular recently. However, how to truly make it serve our daily lives remains an open question. To this end, in this paper, we focus on employing AIGC techniques in one filed of E-commerce marketing, i.e., generating hyper-realistic advertising images for displaying user-specified shoes by human. Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes. It consists of three modules: (1) shoe wearable-area detection module (WD), (2) leg-pose synthesis module (LpS) and the final (3) shoe-wearing image generation module (SW). Them three are performed in ordered stages. Compared to baselines, our ShoeModel is shown to generalize better to different type of shoes and has ability of keeping the ID-consistency of the given shoes, as well as automatically producing reasonable interactions with human. Extensive experiments show the effectiveness of our proposed shoe-wearing system. Figure 1 shows the input and output examples of our ShoeModel. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_04833 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model Chen, Binghui Li, Wenyu Geng, Yifeng Xie, Xuansong Zuo, Wangmeng Computer Vision and Pattern Recognition With the development of the large-scale diffusion model, Artificial Intelligence Generated Content (AIGC) techniques are popular recently. However, how to truly make it serve our daily lives remains an open question. To this end, in this paper, we focus on employing AIGC techniques in one filed of E-commerce marketing, i.e., generating hyper-realistic advertising images for displaying user-specified shoes by human. Specifically, we propose a shoe-wearing system, called Shoe-Model, to generate plausible images of human legs interacting with the given shoes. It consists of three modules: (1) shoe wearable-area detection module (WD), (2) leg-pose synthesis module (LpS) and the final (3) shoe-wearing image generation module (SW). Them three are performed in ordered stages. Compared to baselines, our ShoeModel is shown to generalize better to different type of shoes and has ability of keeping the ID-consistency of the given shoes, as well as automatically producing reasonable interactions with human. Extensive experiments show the effectiveness of our proposed shoe-wearing system. Figure 1 shows the input and output examples of our ShoeModel. |
| title | ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.04833 |